config.json

{
  "layer_share": 1,
  "n_sink": 8,
  "step": 2200,
  "training_config": {
    "model": "Qwen/Qwen3-4B",
    "corpus": "results/raw/corpus/train_A.json",
    "steps": 2200,
    "lr": 5e-05,
    "warmup": 50,
    "layer_share": 1,
    "n_sink": 8,
    "max_chunks": 4,
    "val_docs": 12,
    "val_every": 275,
    "val_examples": 16,
    "clip": 1.0,
    "seed": 0,
    "ckpt": "results/raw/stage2b_extractor.pt",
    "out": "results/raw/stage2b_train.json"
  },
  "target_model": "Qwen/Qwen3-4B",
  "target_model_revision": "1cfa9a7208912126459214e8b04321603b3df60c",
  "n_trainable_params": 566233600,
  "original_pt_sha256": "b8384dd2eeaa87890a6b65e22f791183399764b93dd9a7f4e8a6e4ce13fca425"
}